You are here

A methodology for detecting blood-based abnormalities in wireless capsule endoscopy videos.

Printer-friendly versionPrinter-friendly version
Karargyris A, Bourbakis N
BioInformatics and BioEngineering, 2008. BIBE 2008. 8th IEEE International Conference. 2008 Oct 8; pp 1-6. doi: 10.1109/BIBE.2008.4696806.
Abstract: 

This paper deals with a novel methodology for automatically detecting blood based abnormalities (bleeding, angioectasia and erythema) in wireless capsule endoscopy videos. The methodology is based on a synergistic integration of methods, such as Color K-L transformation, fuzzy region segmentation, Local-Global graphs. The methodology presents several unique features that separate it from the classical bleeding based methods. These features are mainly based on (i) the classification of the blood based pathological cases in three major categories approved by gastroenterologists; (ii) it is based on a synergy of methods tested in the research field for their robustness. Illustrative examples from the methodology are also presented in this paper.

keywords: {biomedical optical imaging;endoscopes;haemodynamics;image classification;image colour analysis;image segmentation;medical disorders;medical image processing;blood-based abnormality detection;color K-L transformation;fuzzy region segmentation;local-global graphs;pathology classification;wireless capsule endoscopy videos;Biomedical imaging;Blood vessels;Color;Endoscopes;Gastrointestinal tract;Hemorrhaging;Intestines;Pixel;Robustness;Videos;Blood Abnormalities;L-G Graphs;Processing and Color transformations;Wireless capsule Endoscopic Imaging}

Karargyris A, Bourbakis N. A methodology for detecting blood-based abnormalities in wireless capsule endoscopy videos. BioInformatics and BioEngineering, 2008. BIBE 2008. 8th IEEE International Conference. 2008 Oct 8; pp 1-6. doi: 10.1109/BIBE.2008.4696806.